English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Bayesian Estimators for Robins-Ritov's Problem

Harmeling, S., & Touissant, M.(2007). Bayesian Estimators for Robins-Ritov's Problem (EDI-INF-RR-1189). Edinburgh, UK: School of Informatics, University of Edinburgh.

Item is

Files

show Files
hide Files
:
Techreport-2007-Harmeling.pdf (Any fulltext), 301KB
Name:
Techreport-2007-Harmeling.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Harmeling, S1, Author              
Touissant, M, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Bayesian or likelihood-based approaches to data analysis became very popular in the field of Machine Learning. However, there exist theoretical results which question the general applicability of such approaches; among those a result by Robins and Ritov which introduce a specific example for which they prove that a likelihood-based estimator will fail (i.e. it does for certain cases not converge to a true parameter estimate, even given infinite data). In this paper we consider various approaches to formulate likelihood-based estimators in this example, basically by considering various extensions of the presumed generative model of the data. We can derive estimators which are very similar to the classical Horvitz-Thompson and which also account for a priori knowledge of an observation probability function.

Details

show
hide
Language(s):
 Dates: 2007-10
 Publication Status: Published in print
 Pages: 12
 Publishing info: Edinburgh, UK : School of Informatics, University of Edinburgh
 Table of Contents: -
 Rev. Type: -
 Identifiers: Report Nr.: EDI-INF-RR-1189
BibTex Citekey: 6326
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show